Open Access. Powered by Scholars. Published by Universities.®
Medical Biomathematics and Biometrics Commons™
Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 23 of 23
Full-Text Articles in Medical Biomathematics and Biometrics
Social Marketing, Stages Of Change, And Public Health Smoking Interventions, Paula Diehr
Social Marketing, Stages Of Change, And Public Health Smoking Interventions, Paula Diehr
Paula Diehr
As a "thought experiment," the authors used a modified stages of change model for smoking to define homogeneous segments within various hypothetical populations. The authors then estimated the population effect of public health interventions that targeted the different segments. Under most assumptions, interventions that emphasized primary and secondary prevention, by targeting the Never Smoker, Maintenance, or Action segments, resulted in the highest nonsmoking life expectancy. This result is consistent with both social marketing and public health principles. Although the best thing for an individual smoker is to stop smoking, the greatest public health benefit is achieved by interventions that target …
Health Benefits Of Increased Walking For Sedentary, Generally Healthy Older Adults: Using Longitudinal Data To Approximate An Intervention Trial, Paula Diehr
Paula Diehr
BACKGROUND: Older adults are often advised to walk more, but randomized trials have not conclusively established the benefits of walking in this age group. Typical analyses based on observational data may have biased results. Here, we propose a "limited-bias," more interpretable estimate of the health benefits to sedentary healthy older adults of walking more, using longitudinal data from the Cardiovascular Health Study. METHODS: The number of city blocks walked per week, collected annually, was classified as sedentary (<7 blocks per>week), somewhat active, or active (>or=28). Analysis was restricted to persons sedentary and healthy in the first 2 years. In Year …
Age-Specific Prevalence And Years Of Healthy Life In A System With 3 Health States, Paula Diehr
Age-Specific Prevalence And Years Of Healthy Life In A System With 3 Health States, Paula Diehr
Paula Diehr
Consider a 3-state system with one absorbing state, such as Healthy, Sick, and Dead. Over time, the prevalence of the Healthy state will approach an 'equilibrium' value that is independent of the initial conditions. We derived this equilibrium prevalence (Prev:Equil) as a function of the local transition probabilities. We then used Prev:Equil to estimate the expected number of years spent in the healthy state over time. This estimate is similar to the one calculated by multi-state life table methods, and has the advantage of having an associated standard error. In longitudinal data for older adults, the standard error was accurate …
Accounting For Missing Data In End-Of-Life Research, Paula Diehr, Laura Lee Johnson
Accounting For Missing Data In End-Of-Life Research, Paula Diehr, Laura Lee Johnson
Paula Diehr
End-of-life studies are likely to have missing data because sicker persons are less likely to provide information and because measurements cannot be made after death. Ignoring missing data may result in data that are too favorable, because the sickest persons are effectively dropped from the analysis. In a comparison of two groups, the group with the most deaths and missing data will tend to have the most favorable data, which is not desirable. Results based on only the available data may not be generalizable to the original study population. If most of the missing data are absent because of death, …
Methods For Incorporating Death Into Health-Related Variables In Longitudinal Studies, Paula Diehr
Methods For Incorporating Death Into Health-Related Variables In Longitudinal Studies, Paula Diehr
Paula Diehr
BACKGROUND AND OBJECTIVES: Longitudinal studies of health over time may be misleading if some people die. Self-rated health (excellent to poor) and the SF-36 profile scores have been transformed to incorporate death. We applied the same approaches to incorporate death into activities of daily living difficulties (ADLs), IADLs, mini-mental state examination, depressive symptoms, blocks walked per week, bed days, the timed walk, body mass index and blood pressure. STUDY DESIGN AND SETTING: The Cardiovascular Health Study of 5,888 older adults, was followed up to 9 years. Mean age was 73 at baseline, and 658 had an incident stroke during follow-up. …
Reliability, Effect Size, And Responsiveness Of Health Status Measures In The Design Of Randomized And Cluster-Randomized Trials, Paula Diehr
Paula Diehr
BACKGROUND: New health status survey instruments are often described by their psychometric (measurement) properties, such as Validity, Reliability, Effect Size, and Responsiveness. For cluster-randomized trials, another important statistic is the Intraclass Correlation (ICC) for the instrument within clusters. Studies using better instruments can be performed with smaller sample sizes, but better instruments may be more expensive in terms of dollars, opportunity cost, or poorer data quality due to the response burden of longer instruments. METHODS: We defined the psychometric statistics in terms of a mathematical model, and examined the power of a two-sample test as a function of the test-retest …
Imputation Of Missing Longitudinal Data: A Comparison Of Methods, Paula Diehr, Jean Mundahl Engels
Imputation Of Missing Longitudinal Data: A Comparison Of Methods, Paula Diehr, Jean Mundahl Engels
Paula Diehr
BACKGROUND AND OBJECTIVES: Missing information is inevitable in longitudinal studies, and can result in biased estimates and a loss of power. One approach to this problem is to impute the missing data to yield a more complete data set. Our goal was to compare the performance of 14 methods of imputing missing data on depression, weight, cognitive functioning, and self-rated health in a longitudinal cohort of older adults. METHODS: We identified situations where a person had a known value following one or more missing values, and treated the known value as a "missing value." This "missing value" was imputed using …
The Importance Of The Normality Assumption In Large Public Health Data Sets, Paula Diehr, Thomas Lumley
The Importance Of The Normality Assumption In Large Public Health Data Sets, Paula Diehr, Thomas Lumley
Paula Diehr
It is widely but incorrectly believed that the t-test and linear regression are valid only for Normally distributed outcomes. The t-test and linear regression compare the mean of an outcome variable for different subjects. While these are valid even in very small samples if the outcome variable is Normally distributed, their major usefulness comes from the fact that in large samples they are valid for any distribution. We demonstrate this validity by simulation in extremely non-Normal data. We discuss situations in which in other methods such as the Wilcoxon rank sum test and ordinal logistic regression (proportional odds model) have …
Transforming Self-Rated Health And The Sf-36 Scales To Include Death And Improve Interpretability, Paula Diehr
Transforming Self-Rated Health And The Sf-36 Scales To Include Death And Improve Interpretability, Paula Diehr
Paula Diehr
BACKGROUND: Most measures of health-related quality of life are undefined for people who die. Longitudinal analyses are often limited to a healthier cohort (survivors) that cannot be identified prospectively, and that may have had little change in health. OBJECTIVE: To develop and evaluate methods to transform a single self-rated health item (excellent to poor; EVGGFP) and the physical component score of the SF-36 (PCS) to new variables that include a defensible value for death. METHODS: Using longitudinal data from two large studies of older adults, health variables were transformed to the probability of being healthy in the future, conditional on …
Probabilities Of Transition Among Health States For Older Adults, Paula Diehr
Probabilities Of Transition Among Health States For Older Adults, Paula Diehr
Paula Diehr
GOAL: To estimate the probabilities of transition among self-rated health states for older adults, and examine how they vary by age and sex. METHODS: We used self-rated health (excellent, very good, good, fair, poor, dead) collected in two longitudinal studies of older adults (mean age 75) to estimate the probability of transition in 2 years. We used the estimates to project future health for selected cohorts. FINDINGS: These older adults were most likely to be in the same health state 2 years later, but a substantial proportion changed in both directions. Transition probabilities varied by initial health state, age and …
Measuring The "Managedness" And Covered Benefits Of Health Plans, Paula Diehr, David Grembowski
Measuring The "Managedness" And Covered Benefits Of Health Plans, Paula Diehr, David Grembowski
Paula Diehr
STUDY AIMS: (1) To develop indexes measuring the degree of managedness and the covered benefits of health insurance plans, (2) to describe the variation in these indexes among plans in one health insurance market, (3) to assess the validity of the health plan indexes, and (4) to examine the association between patient characteristics and the health plan indexes. Measures of the "managedness" and covered benefits of health plans are requisite for studying the effects of managed care on clinical practice and health system performance, and they may improve people's understanding of our complex health care system. DATA SOURCES/STUDY SETTING: As …
Survival Versus Years Of Healthy Life; Which Is More Powerful As A Study Outcome?, Paula Diehr
Survival Versus Years Of Healthy Life; Which Is More Powerful As A Study Outcome?, Paula Diehr
Paula Diehr
Studies of interventions that are intended to improve patients' health are often evaluated with survival as the primary outcome, even when a measure adjusted for quality of survival, such as years of healthy life (YHL), would seem more appropriate. The purpose of this article is to determine whether studies based on survival are more or less powerful than studies based on YHL in clinical trials where either measure might be appropriate. We used data from the Cardiovascular Health Study (CHS) to estimate the sample size that would be needed in studies of 156 different health conditions, for the two outcome …
Methods For Analyzing Health Care Utilization And Costs, Paula Diehr
Methods For Analyzing Health Care Utilization And Costs, Paula Diehr
Paula Diehr
Important questions about health care are often addressed by studying health care utilization. Utilization data have several characteristics that make them a challenge to analyze. In this paper we discuss sources of information, the statistical properties of utilization data, common analytic methods including the two-part model, and some newly available statistical methods including the generalized linear model. We also address issues of study design and new methods for dealing with censored data. Examples are presented.
Effect Size And Power For Clinical Trials Using Years Of Healthy Life As The Primary Endpoint, Paula Diehr
Effect Size And Power For Clinical Trials Using Years Of Healthy Life As The Primary Endpoint, Paula Diehr
Paula Diehr
Some clinical trials perform repeated measurements on patients over time, plot those measures against time, and summarize the results in terms of the area under the curve. If the measured variable is health status, the summary outcome is sometimes referred to as years of healthy life (YHL), or quality-adjusted life years (QALY). This paper investigates some theoretical and practical aspects of randomized trials designed to assess measures such as YHL. We first derived algebraic expressions for the effect size of YHL measures under several theoretical models of the treatment's effect on health. We used these expressions to examine how the …
Optimal Survey Design For Community Intervention Evaluations: Cohort Or Cross-Sectional?, Paula Diehr
Optimal Survey Design For Community Intervention Evaluations: Cohort Or Cross-Sectional?, Paula Diehr
Paula Diehr
Community intervention evaluations that measure changes over time may conduct repeated cross-sectional surveys, follow a cohort of residents over time, or (often) use both designs. Each survey design has implications for precision and cost. To explore these issues, we assume that two waves of surveys are conducted, and that the goal is to estimate change in behavior for people who reside in the community at both times. Cohort designs are shown to provide more accurate estimates (in the sense of lower mean squared error) than cross-sectional estimates if (1) there is strong correlation over time in an individual's behavior at …
Breaking The Matches In A Paired T-Test For Community Interventions When The Number Of Pairs Is Small, Paula Diehr
Breaking The Matches In A Paired T-Test For Community Interventions When The Number Of Pairs Is Small, Paula Diehr
Paula Diehr
There is considerable interest in community interventions for health promotion, where the community is the experimental unit. Because such interventions are expensive, the number of experimental units (communities) is usually small. Because of the small number of communities involved, investigators often match treatment and control communities on demographic variables before randomization to minimize the possibility of a bad split. Unfortunately, matching has been shown to decrease the power of the design when the number of pairs is small, unless the matching variable is very highly correlated with the outcome variable (in this case, with change in the health behaviour). We …
Including Deaths When Measuring Health Status Over Time, Paula Diehr
Including Deaths When Measuring Health Status Over Time, Paula Diehr
Paula Diehr
Measuring health status over time is problematic when some subjects die, because death does not have a defined value on most health status measures. This situation is different from the usual missing data problem because the health status of the dead is, in a sense, known. We examined eight strategies for incorporating deaths into such analyses using three health status measures taken from two data sets, after which we used computer simulation to explore more fully the effect of deaths. The strategies differed in the amount of influence given to the deaths, varying from none (deaths were discarded) to complete …
Small Area Variation Analysis. Methods For Comparing Several Diagnosis-Related Groups., Paula Diehr
Small Area Variation Analysis. Methods For Comparing Several Diagnosis-Related Groups., Paula Diehr
Paula Diehr
In small-area variation analysis, the variation of health care utilization rates, e.g., admission rates, among small areas is calculated. Frequently, the variation of one diagnosis, diagnosis-related group (DRG), or procedure is compared with the variation of another. Unfortunately, the methods generally used to make these comparisons are not consistent. They differ on whether they 1) adjust for the prevalence of the DRGs, 2) distinguish between variation among areas and variation within areas, 3) weight all areas equally, and 4) adjust for multiple admissions per person. None has an associated confidence interval. These discrepancies occur in part because there is no …
Can Small-Area Analysis Detect Variation In Surgery Rates? The Power Of Small-Area Variation Analysis., Paula Diehr
Can Small-Area Analysis Detect Variation In Surgery Rates? The Power Of Small-Area Variation Analysis., Paula Diehr
Paula Diehr
A variety of statistical methods can be used in small-area analysis to test whether there is more variation than would be expected by chance alone. However, the power of these methods to detect existing variation has never been studied. The authors used data regarding back surgery in Washington State to suggest several types of variation that might exist (alternative hypotheses), and then used computer simulation to determine the power, or the probability of detecting this variation. The chi-square test had the highest power of all methods considered against most alternative hypotheses. Power is higher if there are no multiple admissions, …
Reproducibility And Responsiveness Of Health Status Measures. Statistics And Strategies For Evaluation, Paula Diehr, Richard Deyo
Reproducibility And Responsiveness Of Health Status Measures. Statistics And Strategies For Evaluation, Paula Diehr, Richard Deyo
Paula Diehr
Before being introduced to wide use, health status instruments should be evaluated for reliability and validity. Increasingly, they are also tested for responsiveness to important clinical changes. Although standards exist for assessing these properties, confusion and inconsistency arise because multiple statistics are used for the same property; controversy exists over how to measure responsiveness; many statistics are unavailable on common software programs; strategies for measuring these properties vary; and it is often unclear how to define a clinically important change in patient status. Using data from a clinical trial of therapy for back pain, we demonstrate the calculation of several …
Estimating County Percentages Of People Without Health Insurance, Paula Diehr
Estimating County Percentages Of People Without Health Insurance, Paula Diehr
Paula Diehr
County data on the percentage of people without health insurance are seldom available, although state program planning requires such information. As part of an evaluation of Washington's Basic Health Plan (BHP), we conducted a telephone survey in nine Washington counties to estimate the percentage of people under the age of 65 who were uninsured. We used regression analysis to estimate the percentage uninsured in a county as a function of the percentage unemployed. Two validation approaches yielded very good results, suggesting that the equation could be used to estimate the percentage uninsured in unsurveyed counties. The variation ranged from 15% …
What Is Too Much Variation? The Null Hypothesis In Small-Area Analysis, Paula Diehr
What Is Too Much Variation? The Null Hypothesis In Small-Area Analysis, Paula Diehr
Paula Diehr
A small-area analysis (SAA) in health services research often calculates surgery rates for several small areas, compares the largest rate to the smallest, notes that the difference is large, and attempts to explain this discrepancy as a function of service availability, physician practice styles, or other factors. SAAs are often difficult to interpret because there is little theoretical basis for determining how much variation would be expected under the null hypothesis that all of the small areas have similar underlying surgery rates and that the observed variation is due to chance. We developed a computer program to simulate the distribution …
Regression Analysis In Health Services Research: The Use Of Dummy Variables, Paula Diehr, Lincoln Nayak Polissar
Regression Analysis In Health Services Research: The Use Of Dummy Variables, Paula Diehr, Lincoln Nayak Polissar
Paula Diehr
Dummy variables frequently are used in regression analysis but often in an incorrect fashion. A brief review of examples in the medical care literature showed that the interpretation of dummy variable regression coefficients and their significance was often incorrect or unclear. This article shows how dummy variables can be used and assessed properly. The importance of testing for the joint effect of a group of dummy variables is stressed. It also gives a standard and useful extension of the dummy variable technique to testing for the effect of collections of variables.